Subgroup Identification in Vertically Partitioned Data Using UNIFI Protocol

Abstract: Association rule learning is a popular and well researched method for discovering interesting relations between variables in large databases. It is intended to identify strong rules discovered in databases using different measures of interestingness. Based on the concept of strong rules for discovering regularities between products in large-scale transaction like data recorded by point-of-sale (POS) systems in supermarkets. In data mining, association rules are useful for analysing and predicting customer behaviour. They play an important role in shopping basket data analysis, product clustering, catalogue design and store layout. The proposed work is aimed to implement the protocol used in the existing system to the problem of distributed association rule mining in the vertical data. The proposed work uses unifying lists of locally frequent item sets (UNIFI) protocol to find out the subgroup in vertically partitioned data.

Keywords: Association Rule; Data mining; Horizontally Distributed Databases., Privacy-Preserving.